diff --git a/tests/input_files/samples.multiple_lanes.tsv b/tests/input_files/samples.multiple_lanes.tsv
index 7968fb46b8331974de83555f0ea6d01b0fe08821..13aad1b1f4a034ba0490218aca28bea780b37f01 100644
--- a/tests/input_files/samples.multiple_lanes.tsv
+++ b/tests/input_files/samples.multiple_lanes.tsv
@@ -1,5 +1,5 @@
-sample seqmode fq1 fq2 index_size kmer fq1_3p fq1_5p fq2_3p fq2_5p organism gtf genome sd mean kallisto_directionality alfa_directionality alfa_plus alfa_minus multimappers soft_clip pass_mode libtype fq1_polya_3p fq1_polya_5p fq2_polya_3p fq2_polya_5p
-synthetic_10_reads_paired_synthetic_10_reads_paired pe ../input_files/pe_lane1/synthetic_split_lane1.mate_1.fastq.gz ../input_files/pe_lane1/synthetic_split_lane1.mate_2.fastq.gz 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 --fr fr-firststrand str1 str2 10 EndToEnd None A AAAAAAAAAAAAAAA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX TTTTTTTTTTTTTTT
-synthetic_10_reads_paired_synthetic_10_reads_paired pe ../input_files/pe_lane2/synthetic_split_lane2.mate_1.fastq.gz ../input_files/pe_lane2/synthetic_split_lane2.mate_2.fastq.gz 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 --fr fr-firststrand str1 str2 10 EndToEnd None A AAAAAAAAAAAAAAA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX TTTTTTTTTTTTTTT
-synthetic_10_reads_mate_1_synthetic_10_reads_mate_1 se ../input_files/se_lane1/synthetic_split_lane1.mate_1.fastq.gz XXXXXXXXXXXXXXX 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 --fr fr-firststrand str1 str2 10 EndToEnd None A AAAAAAAAAAAAAAA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX
-synthetic_10_reads_mate_1_synthetic_10_reads_mate_1 se ../input_files/se_lane2/synthetic_split_lane2.mate_1.fastq.gz XXXXXXXXXXXXXXX 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 --fr fr-firststrand str1 str2 10 EndToEnd None A AAAAAAAAAAAAAAA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX
+sample seqmode fq1 fq2 index_size kmer fq1_3p fq1_5p fq2_3p fq2_5p organism gtf genome sd mean multimappers soft_clip pass_mode salmon_code fq1_polya_3p fq1_polya_5p fq2_polya_3p fq2_polya_5p
+synthetic_10_reads_paired_synthetic_10_reads_paired pe ../input_files/pe_lane1/synthetic_split_lane1.mate_1.fastq.gz ../input_files/pe_lane1/synthetic_split_lane1.mate_2.fastq.gz 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 10 EndToEnd None ISF AAAAAAAAAAAAAAA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX TTTTTTTTTTTTTTT
+synthetic_10_reads_paired_synthetic_10_reads_paired pe ../input_files/pe_lane2/synthetic_split_lane2.mate_1.fastq.gz ../input_files/pe_lane2/synthetic_split_lane2.mate_2.fastq.gz 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 10 EndToEnd None ISF AAAAAAAAAAAAAAA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX TTTTTTTTTTTTTTT
+synthetic_10_reads_mate_1_synthetic_10_reads_mate_1 se ../input_files/se_lane1/synthetic_split_lane1.mate_1.fastq.gz XXXXXXXXXXXXXXX 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 10 EndToEnd None SF AAAAAAAAAAAAAAA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX
+synthetic_10_reads_mate_1_synthetic_10_reads_mate_1 se ../input_files/se_lane2/synthetic_split_lane2.mate_1.fastq.gz XXXXXXXXXXXXXXX 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 10 EndToEnd None SF AAAAAAAAAAAAAAA XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX XXXXXXXXXXXXXXX
diff --git a/tests/input_files/samples.tsv b/tests/input_files/samples.tsv
index 4b2630287454e8a7d4dbc7652f1897410a905ef5..db8af5b7930ac839ce395b638b7266e178712a60 100644
--- a/tests/input_files/samples.tsv
+++ b/tests/input_files/samples.tsv
@@ -1,3 +1,3 @@
-sample seqmode fq1 index_size kmer fq1_3p fq1_5p organism gtf genome sd mean multimappers soft_clip pass_mode libtype fq1_polya_3p fq1_polya_5p kallisto_directionality alfa_directionality alfa_plus alfa_minus fq2 fq2_3p fq2_5p fq2_polya_3p fq2_polya_5p
-synthetic_10_reads_paired_synthetic_10_reads_paired pe ../input_files/project1/synthetic.mate_1.fastq.gz 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 10 EndToEnd None A AAAAAAAAAAAAAAAAA XXXXXXXXXXXXXXXXX --fr fr-firststrand str1 str2 ../input_files/project1/synthetic.mate_2.fastq.gz AGATCGGAAGAGCGT XXXXXXXXXXXXX XXXXXXXXXXXXXXXXX TTTTTTTTTTTTTTTTT
-synthetic_10_reads_mate_1_synthetic_10_reads_mate_1 se ../input_files/project2/synthetic.mate_1.fastq.gz 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 10 EndToEnd None A AAAAAAAAAAAAAAAAA XXXXXXXXXXXXXXXXX --fr fr-firststrand str1 str2 XXXXXXXXXXXXX XXXXXXXXXXXXX XXXXXXXXXXXXX XXXXXXXXXXXXX XXXXXXXXXXXXX
+sample seqmode fq1 index_size kmer fq1_3p fq1_5p organism gtf genome sd mean multimappers soft_clip pass_mode salmon_code fq1_polya_3p fq1_polya_5p fq2 fq2_3p fq2_5p fq2_polya_3p fq2_polya_5p
+synthetic_10_reads_paired_synthetic_10_reads_paired pe ../input_files/project1/synthetic.mate_1.fastq.gz 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 10 EndToEnd None ISF AAAAAAAAAAAAAAAAA XXXXXXXXXXXXXXXXX ../input_files/project1/synthetic.mate_2.fastq.gz AGATCGGAAGAGCGT XXXXXXXXXXXXX XXXXXXXXXXXXXXXXX TTTTTTTTTTTTTTTTT
+synthetic_10_reads_mate_1_synthetic_10_reads_mate_1 se ../input_files/project2/synthetic.mate_1.fastq.gz 75 31 AGATCGGAAGAGCACA XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/annotation.gtf ../input_files/homo_sapiens/genome.fa 100 250 10 EndToEnd None SF AAAAAAAAAAAAAAAAA XXXXXXXXXXXXXXXXX XXXXXXXXXXXXX XXXXXXXXXXXXX XXXXXXXXXXXXX XXXXXXXXXXXXX XXXXXXXXXXXXX
diff --git a/tests/input_files/samples_alfa.tsv b/tests/input_files/samples_alfa.tsv
index af1835c28f16f31fe571797e3ae07355d1710e50..3fa91e6247704e3e8430b42c467dbbba208c32e2 100644
--- a/tests/input_files/samples_alfa.tsv
+++ b/tests/input_files/samples_alfa.tsv
@@ -1,5 +1,5 @@
-sample seqmode fq1 index_size kmer fq2 fq1_3p fq1_5p fq2_3p fq2_5p organism gtf genome sd mean multimappers soft_clip pass_mode libtype kallisto_directionality fq1_polya fq2_polya alfa_directionality alfa_plus alfa_minus
-paired_end_R1_on_plus_sense pe XXXXXXXXXXXXX 75 31 XXXXXXXXXXXXX GATCGGAAGAGCACA XXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/quick_start.gtf XXXXXXXXXXXXX 100 250 10 EndToEnd None A --fr AAAAAAAAAAAAAAAAA TTTTTTTTTTTTTTTTT fr-firststrand str1 str2
-paired_end_R1_on_plus_antisense pe XXXXXXXXXXXXX 75 31 XXXXXXXXXXXXX AGATCGGAAGAGCACA XXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/quick_start.gtf XXXXXXXXXXXXX 100 250 10 EndToEnd None A --rf AAAAAAAAAAAAAAAAA TTTTTTTTTTTTTTTTT fr-secondstrand str2 str1
-paired_end_R1_on_minus_sense pe XXXXXXXXXXXXX 75 31 XXXXXXXXXXXXX AGATCGGAAGAGCACA XXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/quick_start.gtf XXXXXXXXXXXXX 100 250 10 EndToEnd None A --fr AAAAAAAAAAAAAAAAA TTTTTTTTTTTTTTTTT fr-firststrand str1 str2
-paired_end_R1_on_minus_antisense pe XXXXXXXXXXXXX 75 31 XXXXXXXXXXXXX AGATCGGAAGAGCACA XXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/quick_start.gtf XXXXXXXXXXXXX 100 250 10 EndToEnd None A --rf AAAAAAAAAAAAAAAAA TTTTTTTTTTTTTTTTT fr-secondstrand str2 str1
+sample seqmode fq1 index_size kmer fq2 fq1_3p fq1_5p fq2_3p fq2_5p organism gtf genome sd mean multimappers soft_clip pass_mode salmon_code fq1_polya fq2_polya
+paired_end_R1_on_plus_sense pe XXXXXXXXXXXXX 75 31 XXXXXXXXXXXXX GATCGGAAGAGCACA XXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/quick_start.gtf XXXXXXXXXXXXX 100 250 10 EndToEnd None ISF AAAAAAAAAAAAAAAAA TTTTTTTTTTTTTTTTT
+paired_end_R1_on_plus_antisense pe XXXXXXXXXXXXX 75 31 XXXXXXXXXXXXX AGATCGGAAGAGCACA XXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/quick_start.gtf XXXXXXXXXXXXX 100 250 10 EndToEnd None ISR AAAAAAAAAAAAAAAAA TTTTTTTTTTTTTTTTT
+paired_end_R1_on_minus_sense pe XXXXXXXXXXXXX 75 31 XXXXXXXXXXXXX AGATCGGAAGAGCACA XXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/quick_start.gtf XXXXXXXXXXXXX 100 250 10 EndToEnd None ISF AAAAAAAAAAAAAAAAA TTTTTTTTTTTTTTTTT
+paired_end_R1_on_minus_antisense pe XXXXXXXXXXXXX 75 31 XXXXXXXXXXXXX AGATCGGAAGAGCACA XXXXXXXXXXXXX AGATCGGAAGAGCGT XXXXXXXXXXXXX homo_sapiens ../input_files/homo_sapiens/quick_start.gtf XXXXXXXXXXXXX 100 250 10 EndToEnd None ISR AAAAAAAAAAAAAAAAA TTTTTTTTTTTTTTTTT
diff --git a/workflow/Snakefile b/workflow/Snakefile
index d46c511b58c1152403ff0b05749cab4a796e34f8..efa402ba99f5fd9ae20d51acca46324188173ca5 100644
--- a/workflow/Snakefile
+++ b/workflow/Snakefile
@@ -17,6 +17,20 @@ samples_table = pd.read_csv(
sep="\t",
)
+# dict for translation of "directionality parameters"
+directionality_dict = {
+ "SF":
+ {"kallisto":"--fr-stranded",
+ "alfa": "forward",
+ "alfa_plus": "str1",
+ "alfa_minus": "str2"},
+ "SR":
+ {"kallisto":"--rf-stranded",
+ "alfa": "reverse",
+ "alfa_plus": "str2",
+ "alfa_minus": "str1"},
+}
+
# Parse YAML rule config file
if 'rule_config' in config and config['rule_config']:
try:
@@ -52,6 +66,12 @@ def get_sample(column_id, search_id=None, search_value=None):
else:
return str(samples_table[column_id][0])
+def get_directionality(salmon_code, tool):
+ """ Get directionality value for different tools"""
+ for key in directionality_dict.keys():
+ if key in salmon_code:
+ return directionality_dict[key][tool]
+
def parse_rule_config(rule_config: dict, current_rule: str, immutable: Tuple[str, ...] = ()):
"""Get rule specific parameters from rule_config file"""
@@ -1295,10 +1315,10 @@ rule rename_star_rpm_for_alfa:
"{sample}_Signal.{unique}.{plus}.out.bg"),
sample=wildcards.sample,
unique=wildcards.unique,
- plus=get_sample(
- 'alfa_plus',
+ plus=get_directionality(get_sample(
+ 'salmon_code',
search_id='index',
- search_value=wildcards.sample)),
+ search_value=wildcards.sample),"alfa_plus")),
minus = lambda wildcards:
expand(
os.path.join(
@@ -1309,10 +1329,10 @@ rule rename_star_rpm_for_alfa:
"{sample}_Signal.{unique}.{minus}.out.bg"),
sample=wildcards.sample,
unique=wildcards.unique,
- minus=get_sample(
- 'alfa_minus',
+ minus=get_directionality(get_sample(
+ 'salmon_code',
search_id='index',
- search_value=wildcards.sample))
+ search_value=wildcards.sample), "alfa_minus"))
output:
plus = temp(os.path.join(
@@ -1490,10 +1510,10 @@ rule alfa_qc:
os.path.basename(input.minus),
name = "{sample}",
alfa_orientation = lambda wildcards:
- get_sample(
- 'alfa_directionality',
- search_id='index',
- search_value=wildcards.sample),
+ get_directionality(get_sample(
+ 'salmon_code',
+ search_id='index',
+ search_value=wildcards.sample),"alfa"),
additional_params = parse_rule_config(
rule_config,
current_rule=current_rule,
diff --git a/workflow/rules/paired_end.snakefile.smk b/workflow/rules/paired_end.snakefile.smk
index 37c55460935a5bc1c86716f3ad69efc96e7e5fde..11428959b83b839a7562983aec5da88c9cc7c0db 100644
--- a/workflow/rules/paired_end.snakefile.smk
+++ b/workflow/rules/paired_end.snakefile.smk
@@ -390,7 +390,7 @@ rule pe_quantification_salmon:
"{sample}.salmon.pe"),
libType = lambda wildcards:
get_sample(
- 'libtype',
+ 'salmon_code',
search_id='index',
search_value=wildcards.sample),
additional_params = parse_rule_config(
@@ -489,10 +489,10 @@ rule pe_genome_quantification_kallisto:
"{sample}",
"quant_kallisto"),
directionality = lambda wildcards:
- get_sample(
- 'kallisto_directionality',
- search_id='index',
- search_value=wildcards.sample),
+ get_directionality(get_sample(
+ 'salmon_code',
+ search_id='index',
+ search_value=wildcards.sample),"kallisto"),
additional_params = parse_rule_config(
rule_config,
current_rule=current_rule,
@@ -529,7 +529,7 @@ rule pe_genome_quantification_kallisto:
-i {input.index} \
-o {params.output_dir} \
-t {threads} \
- {params.directionality}-stranded \
+ {params.directionality} \
{params.additional_params} \
--pseudobam \
{input.reads1} {input.reads2} > {output.pseudoalignment}) \
diff --git a/workflow/rules/single_end.snakefile.smk b/workflow/rules/single_end.snakefile.smk
index e270aba84b8a70d69780aa5f31891b991dc8f54f..fd210337cbd6686614c89c412f89e4719ec242c4 100644
--- a/workflow/rules/single_end.snakefile.smk
+++ b/workflow/rules/single_end.snakefile.smk
@@ -329,7 +329,7 @@ rule quantification_salmon:
"{sample}.salmon.se"),
libType = lambda wildcards:
get_sample(
- 'libtype',
+ 'salmon_code',
search_id='index',
search_value=wildcards.sample),
fraglen = lambda wildcards:
@@ -442,10 +442,10 @@ rule genome_quantification_kallisto:
search_id='index',
search_value=wildcards.sample),
directionality = lambda wildcards:
- get_sample(
- 'kallisto_directionality',
- search_id='index',
- search_value=wildcards.sample),
+ get_directionality(get_sample(
+ 'salmon_code',
+ search_id='index',
+ search_value=wildcards.sample),"kallisto"),
additional_params = parse_rule_config(
rule_config,
current_rule=current_rule,
@@ -484,7 +484,7 @@ rule genome_quantification_kallisto:
-l {params.fraglen} \
-s {params.fragsd} \
-t {threads} \
- {params.directionality}-stranded \
+ {params.directionality} \
{params.additional_params} \
--pseudobam \
{input.reads} > {output.pseudoalignment};) \